{"adoption": {"forks": 120, "observed_at": "2026-08-28T04:03:46.012271+00:00", "stars": 1147}, "canonical_url": "https://ross.abutalabs.com/products/hazyresearch-data-centric-ai", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Resources for Data Centric AI", "domain": ["machine-learning", "data-science", "artificial-intelligence", "tutorials"], "enriched": true, "function": ["documentation", "machine-learning"], "health_score": 20, "homepage": null, "language": "TeX", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["HazyResearch/data-centric-ai"], "name": "HazyResearch/data-centric-ai", "platform": ["cross-platform"], "pushed_at": "2023-12-13T09:58:57+00:00", "repo": "HazyResearch/data-centric-ai", "stars": 1147, "tags": ["data-centric-ai", "curated-list", "awesome-list", "research-resources", "mlops", "data-quality"], "topics": ["machine-learning", "ai", "artificial-intelligence", "data-centric-ai"], "urls": [], "use_cases": ["learn about data-centric ai", "find papers on weak supervision and data programming", "study data augmentation and cleaning techniques for machine learning", "prepare a course or reading list on data quality for ML", "explore mlops and data selection resources", "understand why data matters more than models in production ai"], "what_it_is": "A curated, opinionated collection of resources, papers, and progress on Data-Centric AI from the Hazy Research group at Stanford. It organizes topics like weak supervision, data augmentation, data cleaning, robustness, and MLOps into a structured reading guide.", "when_to_avoid": ["you need runnable code, libraries, or tools rather than reading material", "you need up-to-date coverage, as several sections are stubs or under construction", "you want an unbiased survey rather than an opinionated viewpoint"], "when_to_choose": ["you want a curated starting point for data-centric AI research and concepts", "you are building a curriculum or self-study plan around data quality in ML", "you want links to papers, case studies, and related awesome lists in one place"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/hazyresearch-data-centric-ai", "repo": "HazyResearch/data-centric-ai", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.012271+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:33:53.403433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eac8f310cac6651174bb0663d498985feba3e0a776b4be1e2c932429c7854f5", "fetched_at": "2026-08-28T04:03:46.012271+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/data-centric-ai"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.012271+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:33:53.403433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eac8f310cac6651174bb0663d498985feba3e0a776b4be1e2c932429c7854f5", "fetched_at": "2026-08-28T04:03:46.012271+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/data-centric-ai"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:33:53.403433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eac8f310cac6651174bb0663d498985feba3e0a776b4be1e2c932429c7854f5", "fetched_at": "2026-08-28T04:03:46.012271+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/data-centric-ai"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.012271+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.012271+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.012271+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:33:53.403433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eac8f310cac6651174bb0663d498985feba3e0a776b4be1e2c932429c7854f5", "fetched_at": "2026-08-28T04:03:46.012271+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/data-centric-ai"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.012271+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.012271+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:33:53.403433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eac8f310cac6651174bb0663d498985feba3e0a776b4be1e2c932429c7854f5", "fetched_at": "2026-08-28T04:03:46.012271+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/data-centric-ai"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.012271+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.012271+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.012271+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:33:53.403433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eac8f310cac6651174bb0663d498985feba3e0a776b4be1e2c932429c7854f5", "fetched_at": "2026-08-28T04:03:46.012271+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/data-centric-ai"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.012271+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:46.012271+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:33:53.403433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eac8f310cac6651174bb0663d498985feba3e0a776b4be1e2c932429c7854f5", "fetched_at": "2026-08-28T04:03:46.012271+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/data-centric-ai"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:33:53.403433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eac8f310cac6651174bb0663d498985feba3e0a776b4be1e2c932429c7854f5", "fetched_at": "2026-08-28T04:03:46.012271+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/data-centric-ai"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:33:53.403433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eac8f310cac6651174bb0663d498985feba3e0a776b4be1e2c932429c7854f5", "fetched_at": "2026-08-28T04:03:46.012271+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/data-centric-ai"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:33:53.403433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eac8f310cac6651174bb0663d498985feba3e0a776b4be1e2c932429c7854f5", "fetched_at": "2026-08-28T04:03:46.012271+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HazyResearch/data-centric-ai"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1909, "days_push": 994, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}